TY - JOUR
AU1 - Andreoli, André
AU2 - Coury, Denis
AU3 - Oleskovicz, Mario
AU4 - Serni, Paulo
AB - This paper presents a methodology for modeling high intensity discharge lamps based on artificial neural networks. The methodology provides a model which is able to represent the device operating in the frequency of distribution systems, facing events related to power quality. With the aid of a data acquisition system to monitor the laboratory experiment, and using 
$$\text{ MATLAB }^{\textregistered }$$
 software, data was obtained for the training of two neural networks. These neural networks, working together, were able to represent with high fidelity the behavior of a discharge lamp. The excellent performance obtained by these models allowed the simulation of a group of lamps in a distribution system with shorter simulation time when compared to mathematical models. This fact justified the application of this family of loads in electric power systems. The representation of the device facing power quality disturbances also proved to be a useful tool for more complex studies in distribution systems.
TI - Artificial Neural Network Model of Discharge Lamps in the Power Quality Context
JF - Journal of Control, Automation and Electrical Systems
DO - 10.1007/s40313-013-0027-0
DA - 2013-04-25
UR - https://www.deepdyve.com/lp/springer-journals/artificial-neural-network-model-of-discharge-lamps-in-the-power-NOcSKQa6vm
SP - 272
EP - 285
VL - 24
IS - 3
DP - DeepDyve
ER -